alamb commented on code in PR #6231:
URL: https://github.com/apache/arrow-rs/pull/6231#discussion_r1723564296
##########
arrow-string/src/predicate.rs:
##########
@@ -114,38 +114,117 @@ impl<'a> Predicate<'a> {
Predicate::IEqAscii(v) => BooleanArray::from_unary(array,
|haystack| {
haystack.eq_ignore_ascii_case(v) != negate
}),
- Predicate::Contains(finder) => BooleanArray::from_unary(array,
|haystack| {
- finder.find(haystack.as_bytes()).is_some() != negate
- }),
- Predicate::StartsWith(v) => BooleanArray::from_unary(array,
|haystack| {
- starts_with(haystack, v, equals_kernel) != negate
- }),
- Predicate::IStartsWithAscii(v) => BooleanArray::from_unary(array,
|haystack| {
- starts_with(haystack, v, equals_ignore_ascii_case_kernel) !=
negate
- }),
- Predicate::EndsWith(v) => BooleanArray::from_unary(array,
|haystack| {
- ends_with(haystack, v, equals_kernel) != negate
- }),
- Predicate::IEndsWithAscii(v) => BooleanArray::from_unary(array,
|haystack| {
- ends_with(haystack, v, equals_ignore_ascii_case_kernel) !=
negate
- }),
+ Predicate::Contains(finder) => {
+ if let Some(string_view_array) =
array.as_any().downcast_ref::<StringViewArray>() {
+ BooleanArray::from(
+ string_view_array
+ .bytes_iter()
+ .map(|haystack| finder.find(haystack).is_some() !=
negate)
+ .collect::<Vec<_>>(),
+ )
+ } else {
+ BooleanArray::from_unary(array, |haystack| {
+ finder.find(haystack.as_bytes()).is_some() != negate
+ })
+ }
+ }
+ Predicate::StartsWith(v) => {
+ if let Some(string_view_array) =
array.as_any().downcast_ref::<StringViewArray>() {
+ BooleanArray::from(
+ string_view_array
+ .prefix_bytes_iter(v.len())
+ .map(|haystack| {
+ starts_with_bytes(haystack, v.as_bytes(),
equals_kernel) != negate
+ })
+ .collect::<Vec<_>>(),
+ )
+ } else {
+ BooleanArray::from_unary(array, |haystack| {
+ starts_with(haystack, v, equals_kernel) != negate
+ })
+ }
+ }
+ Predicate::IStartsWithAscii(v) => {
+ if let Some(string_view_array) =
array.as_any().downcast_ref::<StringViewArray>() {
+ BooleanArray::from(
+ string_view_array
+ .prefix_bytes_iter(v.len())
+ .map(|haystack| {
+ starts_with_bytes(
Review Comment:
since `prefix` returns at most `v.len()` bytes can this closure simply check
that `haystack == v` with `equals_ignore_ascii_case_kernel`
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
